Komunitas
lemmy.deadca.de
AMD Drivers: Good news! They work even better on Linux. Bad news, you’re probably referring to the AMD “control panel” type application instead of the drivers themselves, which doesn’t have a direct equivalent. The drivers should come pre-installed, though depening on distro you may need to select/install “radv” or “vulkan-radeon” manually. Most of the control panel functionality can be found in other applications, like OBS for recording or CoreCtrl for clock speeds. Chrome: Although Firefox is pre-installed in most cases, you have full freedom of choice here. Most people find that Firefox works basically the same after using it for a bit, but if it doesn’t fit you, there’s other options. Google Chrome is most likely available in your distros app store, but there’s also less “spying” options like ungoogled-chromium. Gmail: You can access this on the website, or through a mail client like thunderbird. You can switch if you want to, you’re not limited by any means here. Office 360: Though LibreOffice is a great alternative, some find themselves forced to use MS office for compatibility reasons. This is still possible, buy only in a webbrowser. ITunes: This is a hard one to find alternatives for, depending on what you use it for. For managing iPhones from a PC, you essentially need Windows or macOS. For playing music, there’s plenty of options. JBL: I’m unsure as I don’t use any of their products, but assuming you mean audio related “control panels”, there’s many options available. Though they may need a bit of tweaking and searching around to get things to sound the way you want. Musescore: I also don’t use this, but it’s available on Flathub, meaning you can (and probably should) use your distros “App Store” to install this. Norton AV: Not many AVs targeting Linux exist, and they’re not the greatest quality. Though it’s doable to go without one, as long as you don’t download and run random files off the internet. Stick to the app store, and you should be totally fine. PyCharm: This is available on Linux, also in the “app store”. There’s other IDEs available too, like vscode. Remote Desktop to iOS: I haven’t owned an iOS device since 2019, so I don’t know which protocol they use. It’s possible this isn’t supported at all. Star Citizen: It looks like this is playable through Proton. You can use Steam (add non-steam game), Lutris, or Bottles to launch non-steam Windows apps/games. Steam: Works great VPN: As you didn’t put a previous VPN provider here, I’m not able to tell you if it works on Linux. Personally I have a hard time recommending any VPN service, but Mullvad stands out as being the least untrustworthy. Almost all others like Nord, Express, etc. share some common traits that make them very untrustworthy to me. Windows Games: This is a bit more complicated. Games from the Microsoft Store are very unlikely to run, and require messing about to even try in the first place. Other games made for Windows likely work (even outside Steam), using management tools like Lutris or Bottles is often easier than manually using Wine. If a tool (or distro) works well for you, it’s a good option. Everyone has different opinions on the “best” distro, but since it’s very subjective, there is no single “best” distro. There’s only 2 distros I recommend against, that’s Ubuntu (and close spin-offs) and Manjaro, because they have major objective downsides compared to equivalents like Mint or Endeavour. The distros I generally recommend to new users are Mint and Fedora, but feel free to look around, you’re not forced to pick a specific one. You noted you were likely going to choose Linux Mint, great! It’s a “stable” distro, as in, it doesn’t change much with small updates. Instead, new release versions (23, 24, 25, etc) come with new changes. Linux Mint comes with an App Store that can install from Flathub, which should be the first place to check for installing new applications. As for VR, it depends heavily on which exact headset you have, and is not always a great experience on Linux right now (speaking from experience with an Index). The LVRA wiki is a great starting place: https://lvra.gitlab.io/. If you’re on a Quest, WiVRN and ALVR exist, though they both have their own downsides. If you’re on a PCVR headset from Oculus, your options are more limited. You might also want to consider a different distro, as VR development is moving very fast. Many VR users choose to go with a “harder” rolling release distribution, like EndeavourOS, to receive feature updates quicker. Also of note, if you have the storage space, you can choose to “dual boot” (even with just one drive). This will give you a menu to choose between Windows and Linux when starting your computer, and will give you time to move stuff over. I generally recommend this, as it provides an option to immediately do a task you know how to do on Windows, when it’s absolutely required to do the task asap.
Komunitas
piefed.social
TL;DR - Question 1: how bad would it be to mount a NTFS drive and continue using it in NTFS format with Linux? Question 2: should I partition my drive to have separate / partition and /home partition if I’m planning to distro hop? Question 3: can I make Steam use game files on my secondary NTFS HDD? I’m getting fed up with Windows day by day with how slow and chuggy it is. My initial plan to buy a new 1TB SSD for Linux is out of the window thanks to astronomical prices and I’m upset by it. So is how HDD prices are also impacted. I have a 2TB HDD formated in NTFS because back then when I built my PC I didn’t think to try linux so I let it stay in NTFS. This drive is where all my personal files and data is. This is a separate drive from the 500GB NVME drive I use for Windows, which will be wiped for Linux. Currently I also have an external portable SSD as a backup / working storage for my work supplied Windows laptop. I am unsure of the parity of my personal data and files is on the portable SSD with my 2TB HDD. So for the forseeable future the HDD will remain in NTFS and could not be reformated into a Linux friendlier format at the moment. So my Question 1 is, how bad would it be to mount that NTFS HDD drive and continue using and working on it, with Linux? Question 2: I haven’t actually decided really what distro to stick with. I’m in a choice paralysis between trying base Fedora, Nobara, atomic Fedora but not Bazzite, and CachyOS. Regardless what I choose I feel like I might distro hop sooner than later. So should I set a different partition for /home? From what I understand, the advantage would be I wouldn’t have to touch my personal data when I distro hop. As I understand it I can just wipe the / partition for the OS I want try next. The disadvantage is that say moving from Fedora to Arch there could be some binaries or config files that might clash and as a noob I’d be in for a rollercoaster of fixing stuff. Am I wrong in my reading and understanding? But if I’m already putting my personal data on a separate drive from the OS drive, I really shouldn’t be bothering with partitioning the OS drive. The other advantage that I read for having / and /home partitions is that if the system have multiple users, there’s a lot lesser risk of a user might fill the whole drive and preventing the OS to update later. So for a single user system like mine, and having a big storage size that is unlikely to happen anyways and I would only have to bother reinstalling programs every time I distro hop. Edit: further understanding and questions related to Question 2: 2: always, even if not distro hopping. You can use a volume aware filesystem like Btrfs and have @ mounted on / and @home mounted on /home, so you don’t have to pre allocate space for one or another. Many distros will detect this setup and smartly use snapshots to revert upgrades without touching your home dir. Interesting thing I saw yesterday when I “test run” to install Fedora KDE Plasma on a USB stick. I didn’t go through with it, but I noticed that the installer suggest to partition my drive as such: sdc1 - format as efi - /boot/efi sdc2 - format as efi - /boot sdc3 - format as btrfs subvolume - / sdc4 - format as btrfs subvolume - /home Is that a good default? on the page that ask whether to install fedora side by side another OS, full wipe, or manual partition, I noticed that whatever drive I want to use it already have to be non Windows friendly. In my case, my nvme is in NTFS naturally, my HDD is in NTFS as well, and my test USB stick is in exfat. Question 3: I have a few games that I already downloaded and install on the Windows system. I plan to move the games that’s installed on the OS drive to the secondary HDD drive, then use that files for when I install linux on the OS drive. Should I not bother with it instead and just bite the bullet and wipe the game files and download it again? or can I make it work somehow? I have checked that my hardware peripherals such as my mic, game controller, gaming wheel and my audio card works before when I ran a live ISO, so that’s fine on that end, I hope. I don’t think I’ll encounter problems with my NVidia card; and if I do I think there’s enough help out there for me to figure it out. So really it’s these 3 big questions that I’ve thought of the more I research before moving to Linux wholesale. If I need any Windows stuff I always have my work supplied laptop. I only need Windows for work only, and I don’t use any Adobe stuff. I’ll admit that I have asked a few AI my questions, but since my personal data is valuable I don’t trust what their answers are. So that’s why I’m making this post. I’m going to play my ESL card and say that I tried my best to convey what I have in my head as best I can. I’ll be happy to clarify further if my wording doesn’t make sense. TIA.
Komunitas
lemmy.abnormalbeings.space
It’s pretty amazing how well that scales, really. What surprised me the most was, that it also works well for live streams - I witnessed that in action when heise (that huge German tech publisher which recently created their own instance and you may have seen a lot in the trending videos) streamed their live show for the first time. Even on a live stream, towards the middle when I checked, I had more downloaded from peers than from the central server, and more uploaded than downloaded. I also have my instance set up to mirror a lot of videos from trustworthy, popular instances - and even so, traffic statistics show no issues whatsoever so far, if something really does attract lots of concurrent viewers, the p2p feature handles that quite efficiently. Now, if only storage was trivial in cost, too, costs for running PeerTube would basically be the same as for text/image-focused Fediverse stuff.
Komunitas
lemmy.ml
Maybe I’ve found a definitive solution, because adblocking only works for a few days, until Google noticed it and put contrameasures. In Firefox install Tampermonkey and in it this script https://greasyfork.org/en/scripts/477725-youtube-iframe-adblocker In Vivaldi no need of Tampermonkey, download the link to an folder and don’t delete it. Open the Extension page in developer mode and drag the script in it. Done It is an ingenious userscript that helps persistent YouTube viewers bypass the frustrating “Ad blockers are not allowed on YouTube” message. It employs a clever technique of dynamically inserting an iframe player to replace the standard YouTube player. This method effectively circumvents YouTube’s ad-blocker detection, allowing for an uninterrupted, ad-free viewing experience even after YouTube’s standard measures have been triggered. So you can still use your adblocker without problems.
Komunitas
lemmy.world
Maybe you have downloaded the wrong APK, there are some bad actors providing “pre built YouTube Revanced APKs”. Be sure to only download the Revanced Manager from https://revanced.app/ and the unpatched YT APK (version should match the recommended one in the manager) from a trusted source like apkpure etc.
Komunitas
lemmygrad.ml
USSR produced many firsts in the realm of science and technology: 1957: First intercontinental ballistic missile R-7 Semyorka 1957: First orbiting satellite, Sputnik 1 1957: First living in orbit, the dog Laika on Sputnik 2 1957: First nuclear powered icebreaker “Lenin” weighing in at 19,240 tons of steel 1958: First Tokamak thermonuclear experimental system 1959: First man-made object to leave the Earth’s orbit, Luna 1 1959: First communication to and from Luna 1 with Earth 1959: First object to pass near the moon, and the first object in orbit around the Moon, Luna 1 1959: First satellite hit the moon, Luna 2 1959: First images of the dark side of the moon, Luna 3 1960: First satellite to be launched to Mars, the Marsnik 1 1961: First satellite to Venus, Venera 1 1961: First person to enter orbit around the Earth, Yuri Gagarin in Vostok 1 1961: First person to spend a day in orbit, Gherman Titov – Vostok 2 1962: First flight of two astronauts, Vostok 3 and Vostok 4 1963: First woman in space, Valentina Tereshkova, Vostok 6 1964: First flight of several astronauts, Voskhod 1 1965: First spacewalk, Aleksei Leonov, Voskhod 2 1965: First probe to another planet Venus, Venera 3 1966: First probe to descend on the moon and send from there, Luna 9 1966: First probe in lunar orbit, Luna 10 1967: First meeting of unmanned Cosmos 186/Cosmos 188, this aws not achieved by US until 2006 1969: First docking and crew exchange in orbit, Soyuz 4 and Soyuz 5 1970: First signals sent to the moon by Luna 16 1970: First mobile robot, Lunokhod 1 1970: First data sent by a probe from another planet (Venus), Venera 7 1971: First space station, Salyut 1 1971: First satellite in orbit around Mars and landing on Mars 2 1975: First satellite in orbit around Venus and sending data to earth, Venera 9 1984: First woman to walk in space, Svetlana Savitskaja on Salyut 7 1986: First team to visit two space stations Salyut and Mir 1986: First permanent space station in Earth orbit from 1986 to 2001, MIR 1987: First team to spend more than a year aboard Mir, Vladimir Titov and Musa Manarov These are just some of the biggest technological and social achievements of the Soviet Union. academic studies on USSR Professor of Economic History, Robert C. Allen, concludes in his study without the 1917 revolution is directly responsible for rapid growth that made the achievements listed above possilbe: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.507.8966&rep=rep1&type=pdf Study demonstrating the steady increase in quality of life during the Soviet period (including under Stalin). Includes the fact that Soviet life expectancy grew faster than any other nation recorded at the time: https://www.jstor.org/stable/2672986?seq=1 A large study using world bank data analyzing the quality of life in Capitalist vs Socialist countries and finds overwhelmingly at similar levels of development with socialism bringing better quality of life: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1646771/pdf/amjph00269-0055.pdf This study compared capitalist and socialist countries in measures of the physical quality of life (PQL), taking into account the level of economic development. https://pubmed.ncbi.nlm.nih.gov/2430906/ This study shows that unprecedented mortality crisis struck Eastern Europe during the 1990s, causing around 7 million excess deaths. The first quantitative analysis of the association between deindustrialization and mortality in Eastern Europe. https://academic.oup.com/cje/advance-article/doi/10.1093/cje/beac072/7081084?guestAccessKey=01c8dd9f-af1c-48b3-b271-eb5d3a45017c&login=false So, how do people who lived under communism feel now that they got a taste of capitalism? A remarkable 72% of Hungarians say that most people in their country are actually worse off today economically than they were under communism. Only 8% say most people in Hungary are better off, and 16% say things are about the same. In no other Central or Eastern European country surveyed did so many believe that economic life is worse now than during the communist era. This is the result of almost universal displeasure with the economy. Fully 94% describe the country’s economy as bad, the highest level of economic discontent in the hard hit region of Central and Eastern Europe. Just 46% of Hungarians approve of their country’s switch from a state-controlled economy to a market economy; 42% disapprove of the move away from communism. The public is even more negative toward Hungary’s integration into Europe; 71% say their country has been weakened by the process. The most incredible result was registered in a July 2010 IRES (Romanian Institute for Evaluation and Strategy) poll, according to which 41% of the respondents would have voted for Ceausescu, had he run for the position of president. And 63% of the survey participants said their life was better during communism, while only 23% attested that their life was worse then. Some 68% declared that communism was a good idea, just one that had been poorly applied. Glorification of the German Democratic Republic is on the rise two decades after the Berlin Wall fell. Young people and the better off are among those rebuffing criticism of East Germany as an “illegitimate state.” In a new poll, more than half of former eastern Germans defend the GDR. A poll shows that as many as 81 per cent of Serbians believe they lived best in the former Yugoslavia -“during the time of socialism”. The survey focused on the respondents’ views on the transition “from socialism to capitalism”, and a clear majority said they trusted social institutions the most during the rule of Yugoslav communist president Josip Broz Tito. The standard of living during Tito’s rule from the Second World War to the 1980s was also assessed as best, whereas the Milosevic decade of the 1990s, and the subsequent decade since the fall of his regime are seen as “more or less the same”. 45 percent said they trusted social institutions most under communism with 23 percent choosing the 2001-2003 period when Zoran Djinđic was prime minister. Only 19 per cent selected present-day institutions. 75% of Russians have expressed increasingly positive opinions about the Soviet Union over the years. Only a small portion of those surveyed said they had negative associations with the Soviet Union. The economic deficit, long lines and coupons were named by 4% of respondents each, while the Iron Curtain, economic stagnation and political repressions were named by 1% each, the Levada Center said. Adult mortality increased enormously in Russia and other countries of the former Soviet Union when the Soviet system collapsed 30 years ago. https://archive.ph/9Z12u Former Soviet Countries See More Harm From Breakup https://news.gallup.com/poll/166538/former-soviet-countries-harm-breakup.aspx The Free market paradise goes East chapters in Blackshirts and Reds details some more results of the transition to capitalism.
Komunitas
lemmy.sdf.org
The unearth syntax is like this: usage: unearth [-h] [--verbose] [--index-url URL] [--find-link LOCATION] [--trusted-host HOST] [--no-binary] [--only-binary] [--prefer-binary] [--all] [--link-only] [--download [DIR]] [--python-version PY_VER] [--abis ABIS] [--implementation IMPL] [--platforms PLATFORMS] requirement I want to get the whole list of all wheel files that argostranslate version 1.9.6 is dependent on, because that’s possibly the last version of argos-translate that worked offline. My first attempt: $ unearth --find-link /usr/local/src/argos-translate/wheel_cache/ argostranslate=1.9.6 usage: unearth [-h] [--verbose] [--index-url URL] [--find-link LOCATION] [--trusted-host HOST] [--no-binary PACKAGE] [--only-binary PACKAGE] [--prefer-binary] [--all] [--link-only] [--download [DIR]] requirement unearth: error: argument requirement: invalid Requirement value: 'argostranslate=1.9.6' It does not accept my version constraint, despite examples using that kind of syntax. So I had to do this: $ unearth --all --find-link /usr/local/src/argos-translate/wheel_cache/ argostranslate It dumped metadata on all versions. I picked through the heap of output and found this: { "name": "argostranslate", "version": "1.9.6", "link": { "url": "https://files.pythonhosted.org/packages/01/f9/b472322ea3de4752bbec7fb2f169f057872390a9ff35f72a2142d06392ae/argostranslate-1.9.6-py3-none-any.whl", "comes_from": "https://pypi.org/simple/argostranslate/", "yank_reason": null, "requires_python": ">=3.5", "metadata": null } }, { "name": "argostranslate", "version": "1.9.6", "link": { "url": "https://files.pythonhosted.org/packages/6b/fc/13aa57857bee34f62cb9018c5fd4ec56da714431689b62cca9dce30a8877/argostranslate-1.9.6.tar.gz", "comes_from": "https://pypi.org/simple/argostranslate/", "yank_reason": null, "requires_python": ">=3.5", "metadata": null } }, That just gives the wheel for the app itself, not the wheels it depends on. How can I get the full list of wheels that argostranslate is dependent on using unearth? I should say that I supply the following option because I happen to already have all the wheel files: --find-link /usr/local/src/argos-translate/wheel_cache/ That’s just to feed unearth as well as possible as an experiment. In fact it makes no difference if I omit the --find-link option. The end game is to be able to get this list in the future when I am starting from zero. I might be looking to do something like --verbose --download --dry-run, but there is no --dry-run. My wheel dir (/usr/local/src/argos-translate/wheel_cache/) ::: spoiler currently contains these files annotated_types-0.7.0-py3-none-any.whl argostranslate-1.10.0-py3-none-any.whl blis-1.3.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl catalogue-2.0.10-py3-none-any.whl certifi-2025.11.12-py3-none-any.whl charset_normalizer-3.4.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl click-8.3.1-py3-none-any.whl cloudpathlib-0.23.0-py3-none-any.whl confection-0.1.5-py3-none-any.whl ctranslate2-4.6.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl cymem-2.0.13-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl emoji-2.15.0-py3-none-any.whl filelock-3.20.1-py3-none-any.whl fsspec-2025.12.0-py3-none-any.whl idna-3.11-py3-none-any.whl jinja2-3.1.6-py3-none-any.whl joblib-1.5.3-py3-none-any.whl markupsafe-3.0.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl mpmath-1.3.0-py3-none-any.whl murmurhash-1.0.15-cp311-cp311-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl networkx-3.6.1-py3-none-any.whl numpy-2.4.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl nvidia_cublas_cu12-12.8.4.1-py3-none-manylinux_2_27_x86_64.whl nvidia_cuda_cupti_cu12-12.8.90-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl nvidia_cuda_nvrtc_cu12-12.8.93-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl nvidia_cuda_runtime_cu12-12.8.90-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl nvidia_cudnn_cu12-9.10.2.21-py3-none-manylinux_2_27_x86_64.whl nvidia_cufft_cu12-11.3.3.83-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl nvidia_cufile_cu12-1.13.1.3-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl nvidia_curand_cu12-10.3.9.90-py3-none-manylinux_2_27_x86_64.whl nvidia_cusolver_cu12-11.7.3.90-py3-none-manylinux_2_27_x86_64.whl nvidia_cusparse_cu12-12.5.8.93-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl nvidia_cusparselt_cu12-0.7.1-py3-none-manylinux2014_x86_64.whl nvidia_nccl_cu12-2.27.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl nvidia_nvjitlink_cu12-12.8.93-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl nvidia_nvshmem_cu12-3.3.20-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl nvidia_nvtx_cu12-12.8.90-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl packaging-25.0-py3-none-any.whl preshed-3.0.12-cp311-cp311-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl protobuf-6.33.2-cp39-abi3-manylinux2014_x86_64.whl pydantic-2.12.5-py3-none-any.whl pydantic_core-2.41.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl pyyaml-6.0.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl regex-2025.11.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl requests-2.32.5-py3-none-any.whl sacremoses-0.1.1-py3-none-any.whl sentencepiece-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl setuptools-80.9.0-py3-none-any.whl smart_open-7.5.0-py3-none-any.whl spacy-3.8.11-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl spacy_legacy-3.0.12-py2.py3-none-any.whl spacy_loggers-1.0.5-py3-none-any.whl srsly-2.5.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl stanza-1.10.1-py3-none-any.whl sympy-1.14.0-py3-none-any.whl thinc-8.3.10-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl torch-2.9.1-cp311-cp311-manylinux_2_28_x86_64.whl tqdm-4.67.1-py3-none-any.whl triton-3.5.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl typer_slim-0.21.0-py3-none-any.whl typing_extensions-4.15.0-py3-none-any.whl typing_inspection-0.4.2-py3-none-any.whl urllib3-2.6.2-py3-none-any.whl wasabi-1.1.3-py3-none-any.whl weasel-0.4.3-py3-none-any.whl wrapt-2.0.1-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl ::: I can run unearth on the prefixes of each of those – but that’s cheating, because in a future installation starting with nothing I will not know those packages or versions.
Komunitas
hexbear.net
To be fair anyone who’s foolish to use an on-site encryption feature is foolish. Almost every basic deep web guide explicitly says to use your OS’ pre-downloaded encryption apps and to never trust a site’s encryption.
Komunitas
lemmy.ca
I purchased MSFS several months ago. I was excited to fly the entire world. The game kept crashing (i5 13600k and RTX 4070 Super). After maybe 5 attempts I got past opening the .exe, only to find that the game required 150 gb of updates. No worries, I’ve got fast internet. But guess what? You’re limited to Microsoft’s server speeds, which appeared to be capped at 320 kbps. I would have run through my refund window ages before I’d even have the game downloaded. Do I risk $90 CAD on the hopes that an already struggling to run game actually works? Or do I refund? Tough choice it was for me. Hah. Also special fuck you to Thrustmaster. NEVER waste your money on their absolute garbage. I bought the Boeing 787 yoke and it worked for 3 months before the roll sensor gave out, making it impossible to fly straight because the yoke is detecting random spastic motions all over the place, making the entire thing unusable. If you search this issue online you’ll find tons of people with the same issue. They use a first gen cheap hall sensor for the roll axis that keeps picking up interference from everything (especially the left throttle axis)
Komunitas
ibbit.at
An important aspect in software engineering is the ability to distinguish between premature, unnecessary, and necessary optimizations. A strong case can be made that the initial design benefits massively from optimizations that prevent well-known issues later on, while unnecessary optimizations are those simply do not make any significant difference either way. Meanwhile ‘premature’ optimizations are harder to define, with Knuth’s often quoted-out-of-context statement about these being ‘the root of all evil’ causing significant confusion. We can find Donald Knuth’s full quote deep in the 1974 article Structured Programming with go to Statements, which at the time was a contentious optimization topic. On page 268, along with the cited quote, we see that it’s a reference to making presumed optimizations without understanding their effect, and without a clear picture of which parts of the program really take up most processing time. Definitely sound advice. And unlike back in the 1970s we have today many easy ways to analyze application performance and to quantize bottlenecks. This makes it rather inexcusable to spend more time today vilifying the goto statement than to optimize one’s code with simple techniques like zero-copy and binary message formats. Got To Go Fast The cache hierarchy of the 2008 Intel Nehalem x86 microarchitecture. (Source: Intel) There’s a big difference between having a conceptual picture of how one’s code interacts with the hardware and having an in-depth understanding. While the basic concept of more lines of code (LoC) translating into more RAM, CPU, and disk resources used is technically true much of the time, the real challenge lies in understanding how individual CPU cores are scheduled by the OS, how core cache synchronization works, and the impact that the L2 and L3 cache have. Another major challenge is that of simply moving data around between system RAM, caches and registers, which seems obvious at face value, but the impact of certain decisions can have big implications. For example, passing a pointer to a memory address instead of the entire string, and performing aligned memory accesses instead of unaligned can take more or less time. This latter topic is especially relevant on x86, as this ISA allows unaligned memory access with a major performance penalty, while ARM will hard fault the application at the merest misaligned twitch. I came across a range of these issues while implementing my remote procedure call library NymphRPC. Initially I used a simple and easy to parse binary message format, but saddled it with a naïve parser implementation that involved massive copying of strings, as this was the zero-planning-needed, smooth-brained, ‘safe’ choice. In hindsight this was a design failure with a major necessary optimization omitted that would require major refactoring later. In this article I’d like to highlight both the benefits of simple binary formats as well as how simple it is to implement a zero-copy parser that omits copying of message data during parsing, while also avoiding memory alignment issues when message data is requested and copied to a return value. KISS Perhaps the biggest advantage of binary message formats is that they’re very simple, very small, and extremely low in calories. In the case of NymphRPC its message format features a standard header, a message-specific body, and a terminator. For a simple NymphRPC message call for example we would see something like: uint32 Signature: DRGN (0x4452474e) uint32 Total message bytes following this field. uint8 Protocol version (0x00). uint32 Method ID: identifier of the remote function. uint32 Flags (see Flags section). uint64 Message ID. Simple incrementing global counter. <…> Serialised values. uint8 Message end. None type (0x01). The very first value is a 32-bit unsigned integer that when interpreted as characters identifies this as a valid NymphRPC message. (‘DRGN’, because dragonfly nymph.) This is followed by another uint32 that contains the number of bytes that follow in the message. We’re now eight bytes in and we already have done basic validation and know what size buffer to allocate. Serializing the values is done similarly, with an 8-bit type code followed by the byte(s) that contain the value. This is both easy to parse without complex validation like XML or JSON, and about as light-weight as one can make a format without adding something like compression. Only If Needed When we receive the message bytes on the network socket, we read it into a buffer. Because the second 32-bit value which we read earlier contained the message size, we can make sure to allocate a buffer that’s large enough to fit the rest of the message’s bytes. The big change with zero-copy parsing commences after this, where the naïve approach is to copy the entire byte buffer into e.g. a std::string for subsequent substring parsing. Instead of such a blunt method, the byte buffer is parsed in-place with the use of a moving index pointer into the buffer. The two key methods involved with the parsing can be found in nymph_message.cpp and nymph_types.cpp, with the former providing the NymphMessage constructor and the basic message parser. After parsing the header, the NymphType class provides a parseValue() function that takes a value type code, a reference to the byte buffer and the current index. This function is called until the terminating NYMPH_TYPE_NONE is found, or some error occurs. Looking at parseValue() in more detail, we can see two things of note: the first is that we are absolutely copying certain data despite the ‘zero-copy’ claim, and the liberal use of memcpy() instead of basic assignment statements. The first item is easy to explain: the difference between either copying the memory address or the value of a simple integer/floating point type is so minimal that we trip head-first into the same ‘premature optimization’ thing that Mr. Knuth complained about back in 1974. Ergo we just copy the value and don’t break our pretty little heads about whether doing the same thing in a more convoluted way would net us a few percent performance improvement or loss. This is different with non-trivial types, such as strings. These are simply a char* pointer into the byte buffer, leaving the string’s bytes in peace and quiet until the application demands either that same character pointer via the API or calls the convenience function that assembles a readily-packaged std::string. Memcpy Is Love Although demonizing ‘doing things the C way’ appears to be a popular pastime, if you want to write code that works with the hardware instead of against it, you really want to be able to write some highly performative C code and fully understand it. When I had written the first zero-copy implementation of NymphRPC and had also written up what I thought was a solid article on how well optimized the project now was, I had no idea that I had a “fun” surprise waiting for me. As I happily tried running the new code on a Raspberry Pi SBC after doing the benchmarking for the article on an x86 system, the first thing it did was give me a hard fault message in the shell along with a strongly disapproving glare from the ARM CPU. As it turns out, doing a direct assignment like this is bound to get you into trouble: methodId = ((uint32_t) (binmsg + index)); This line casts the current index into the byte buffer as a uint32_t type before dereferencing it and assigning the value to the variable. When you’re using e.g. std::string the alignment issues sort themselves out somewhere within the depths of the STL, but with direct memory access like this you’re at the mercy of the underlying platform. Which is a shame, because platforms like ARM do not know the word ‘mercy’. Fortunately this is easy to fix: memcpy(&methodId, (binmsg + index), 4); Instead of juggling pointers ourselves, we simply tell memcpy what the target address is, where it should copy from and how many bytes are to be copied. Among all the other complex scenarios that this function has to cope with, doing aligned memory address access for reading and writing is probably among its least complex requirements. Hindsight Looking back on the NymphRPC project so far, it’s clear that some necessary optimizations that ought to have been there from the very beginning weren’t there. At least as far as unnecessary and premature optimizations go, I do feel that I have successfully dodged these, but since these days we’re still having annual flamewars about the merits of using goto I very much doubt that we will reach consensus here. What is clear from the benchmarking that I have done on NymphRPC before and after this major refactoring is that zero-copy makes a massive difference, with especially operations involving larger data (string) chunks becoming multiple times faster, with many milliseconds shaved off and the Callgrind tool of Valgrind no longer listing __memcpy_avx_unaligned_erms as the biggest headache due to std::string abuse. Perhaps the most important lesson from optimizing a library like NymphRPC is that aside from it being both frustrating and fun, it’s also a humbling experience that makes it clear that even as a purported senior developer there’s always more to learn. Even if putting yourself out there with a new experience like porting a lock-free ring buffer to a language like Ada and getting corrected by others stings a little. After all, we are here to write performant software that’s easy to maintain and have fun while doing it, with sharing optimization tips and other tricks just being part of the experience. From Blog – Hackaday via this RSS feed
Komunitas
ibbit.at
Photograph by Nathaniel St. Clair January 3, 2026, should be the date to end all discussion: Trump’s raid on Venezuela should have clarified reality even to the most obtuse: the US is not an “ordinary” country, as is claimed by observers all around, but is the center of the US Empire. Its “leaders” seek to dominate the world. Those of us on the radical left have been correct: the United States is an imperialistcountry, and currently, the most powerful one on the planet. After observing the war in Vietnam, as a US Marine who spent his four years in the United States (1969-73), and taking some time to try to reconsider my thinking after getting out of the military, I began serious writing in 1984, trying to understand what was going on in the world. Obviously, what I had been told while growing up by my family, schools, and government had been a series of lies. Vietnam had not been invaded by an external force; the war there was a civil war, and the United States had, in its arrogance, stuck its nose into. (Years later, I learned that in Geneva during1954, the US had agreed with the French, the Chinese, the Soviets, and “North” Vietnamese to allow the people of “South” Vietnam to have a free and fair election so as to decide whether they wanted to live as an “independent” country under a French puppet regime or if they wanted to join with those in the north of Vietnam, under Ho Chi Minh, to be part of Vietnam. The election was to take place in 1956. That year, the “independent” regime cancelled the agreed-upon elections, which were never held. The reason, according to then-President Dwight Eisenhower in his memoirs, was that ‘Every poll showed that Ho Chi Minh would have won 80 percent of a free, fair election,’ and that’s why 3.8 million Vietnamese were killed and another 5.7 million wounded, and over 58,000 Americans and other allies were killed, and hundreds of thousands were wounded and often traumatized for life. See Turse, 2013.) But that information, which I picked up along the way, was not what I was ultimately seeking; I was trying to figure out how changes in the global economy were affecting US workers (Scipes, 1984). I was, at the time, taking a graduate course in international relations at San Francisco State University while working as a union printer and labor activist in the Bay Area. To try to grasp the economic developments beginning during the late 1970s, I felt it necessary to go back to the end of World War II, in 1945. Trying to begin with the big picture, I recognized that there were two empires in the world, one led by the United States and one by the Union of Soviet Socialist Republics (USSR or Soviet Union) and, while recognizing the existence of each, I concentrated on the US Empire. This was unusual; at that time; no scholar that I found had used this term. [Years later, I learned that William Appleman Williams in his 1959/1962 book had used this term, and then in Black Against Empire by Joshua Bloom and Waldo E. Martin, Jr. (2013), that the Black Panthers had used it during the late 1960s-early ‘70s in presenting their understanding of the world. In 1989, Jan Nederveen Pieterse, a Dutch-born scholar, used the term in his title, Empire and Emancipation. There probably have been others.] And later, the late William Blum (1986, 2000, 2013)—whose work has been so influential upon many US activists—thought he was responsible for revival of the term; when I stayed with him in his apartment in Washington, DC the last time we saw each other—probably somewhere around 2016-18—we discussed this and I showed him I had revived the term before him; obviously, his important books popularized the term far beyond my simple paper. In any case, I think it’s safe to say that I was among the earliest of those who used it after the end of the American war in Vietnam. Yet today, as far as I can tell, I am among only a few who have used the term consistently over the years (for a few examples, see Scipes, 1989, 2010a, 2010b, 2016, 2023), although Alfred W. McCoy finally adopted it in 2017, and he reported in his brilliant Shadows of the American Century (2017) that it had been adopted by a range of scholarly writers; he continues in his 2026 subtitle. Now, I can understand why my limited range of published articles had such a minor impact, but I cannot understand the same for a major distinguished scholar such as McCoy. (In fact, I reviewed his 2017 book in an on-line, peer-reviewed scholarly journal, “Class, Race, and Corporate Power,” in an effort to expand his impact, and as of today, there have been over 4,500 downloads of my review around the world. See Scipes, 2018). What I find shocking, however, is the almost total absence of the term “empire” in the writings of our best political activists today, wherever they are located. And while I’d like to get whatever credit due me for my work, my concern is much larger; to me, the use of empire signifies taking a global approach to the world. And that its absence in our writings suggests strongly that most North American political writers are confining our analysis to the United States of America and, possibly, Canada. (And obviously, we must exempt those living and writing overseas who utilize a global perspective.) To me, if one is writing about the United States in the world, then—almost by definition—this cannot be confined to domestic politics. Period. The folks I see who are doing this seem to have some sort of “social democratic” perspective and politics, whether they claim it or not. These are reformist politics, not radical ones. In other words, rather than to struggle for a new world, they want to “reform” the current one around the edges, so that the jagged parts can be dislodged and then the remainder smoothed off. (I’m trying to be descriptive here, not pejorative.) In general, they do not want to address the reality that the US is an imperialist nation. The problem, from my perspective, is that the United States is acting globally, and has been a global project since Europeans first “found” it. (Rough dating because its existed continuously since then is 1607 in Virginia; there were earlier Spanish and English settlements previously, but they didn’t survive.) In any case, the US has continuously been effecting and effected by global forces since that time. We are not taught this in the overwhelming majority of our schools, including, from what I can tell, most universities. If we were, there would have to be major changes in the “American” story. Let me give on example to clarify. We are taught about the Louisiana Purchase where, in 1803, US President Thomas Jefferson bought most of the US “west” from France (lands other than those claimed at the time by Spain). By why were the French even willing to sell? That is rarely addressed…. In general, the world at the time saw major European powers—especially England, France, and Spain—competing to dominate the world. They each had colonies in the Caribbean; the English in Jamaica, the French in Haiti, and the Spanish in the Dominican Republic and Cuba. These colonies each produced massive amounts of profits from the slave-produced sugar and other natural resources for its imperial master, plus they each had ports for their respective military, both to provide internal control over the slaves and to protect the supply lines to the respective countries from the imperial homeland. This way, they were able to protect respective trading routes from competitors, as well as from independent pirates who preyed on shipping. However, in 1791, the slaves of Haiti under Toussaint L’Ouverture rebelled and overthrew the French colonists. Napoleon then sent the French Army to recapture the colony, but the self-liberated slaves defeated them. The British decided to take advantage of the situation, sent their Army to Haiti and, in turn, were also defeated by the former enslaved. (To put this in contemporary terms, these were like the #1 and #2 competitors for the World Heavyweight Boxing Crown!) Haiti has made to suffer ever since for its impertinence (see Geggus. 2014; James, 1938; Nederveen Pieterse, 1989, Chapter 14). Why haven’t we in the US been taught about the Haitian Revolution of 1791? Simply, it didn’t fit well with the myth of white supremacy to have Black former slaves defeat white armies. This myth had been projected around the world, especially by the white imperialists, to justify their degradation, enslavement, and killing of people of color as the imperialists stole their lands, raw materials, natural resources, and in many cases, their peoples for the well-being of the rich in the imperial countries. The imperialists—including those in the United States, which included most of the white elites—certainly didn’t want to undermine this established myth! Second, the newly liberated Haitians provided political and economic support for forces in northern South America that were fighting under Simon Bolivar for their liberation from Spain, as well as inspiration for Black slave revolts, such as Gabriel Prosser’s and Denmark Vesey’s in the US South. We cannot talk about global solidarity, can we? And third, and immediately pertinent to this article, is that without Haiti, the French could no longer protect their supply lines from the English, Spanish and various pirates, supply lines that had formerly run from France, through Haiti, and on to New Orleans, the headquarters of the French colony in the “American” west. The Revolution in Haiti had deprived the French of their protective bases and maintenance of New Orleans was simply unsustainable without them. Thus, the French cut their losses and sold to the United States and avoided another possible war as US colonists were heading west. I share this story to make my point: we cannot understand the development of nor the actions of the United States in the world today without taking a global perspective. Truthfully, it never has been possible, but this has not been told to us. So, when we fail to place our political understandings, strategies, and tactics in anything other than a global perspective, we are limiting and lying to ourselves and others! It is that clear. And yet, most of the US left fails to take a global perspective; we try to understand the world by limiting our vision to the US and maybe, in a few cases, Canada and Mexico. But wait: what about US support for struggles in Vietnam, Central America, the Philippines, South Africa, Iraq, Afghanistan, Gaza, Venezuela, etc.? Support for each has been strong, albeit some support stronger than others. This support hasbeen impressive, but it has often been detached from our politics as home in the US. In other words, I argue that political struggles in the US have been detached from those overseas. But this is stupid! Yes. Why the disjunction? I believe a major factor here is in the nature of the US left. Most of us, and especially leaders, have gone to college and have at least a bachelor’s degree. [Truth in advertising: not only do I have a Bachelor’s, I have a Master’s and a Ph.D. I taught at a university in Northwest Indiana for 18 ½ years, however, it was after years of serving in the US military, and working for years as an industrial printer, office worker, and high school teacher. Please focus on my argument if possible.] What most people do not recognize is the impact of a college degree. What students learn going through these programs is how to systematically generalize and analyze their subjects, and these are skills that few non-college attendees attain unless they get specific, specialized training as through some union training programs, some military occupational specialties, and/or advanced technical training. At the same time, as my friend, Kayla Vasilko reminds me, “above all college students are taught to compete for the American dream. They are graded against each other to compete for the best jobs, of which there are few. They are taught not to trust others; they are not taught how to work together and organize. They are taught to obey authority.” The importance of recognizing both of these outcomes is that many college grads feel uncomfortable around more working class people, and we fail to interact with them. (I definitely am not suggesting that all working class people are wonderful, much less perfect, or any such thing: they are as good as the best of us and as bad as the worst of us.) Worse, we often denigrate them. (I’d argue that working class people of all colors deserve all the respect each of expect for ourselves, at least until they prove themselves undeserving.) The larger point here being that we have knowledge to share, as well as they have knowledge and experiences to share with us, and we need to directly and forthrightly confront this gap. Without doing this, we lose our major source of power as a political project: people power. We don’t have the guns, we don’t have legal “rights” to stop the mistreatment of us all: the only real potential power we have—as has been shown recently in Los Angeles, Chicago and Portland, Oregon in their resistance to the fascists in the Trump Administration and particularly in ICE—is the power of the people. Yet, how to we build these connections? We have to be able to communicate across our differences in ways that make sense to each other. That means, we must try to understand the world in all of its complexities and be able to convey those understandings in ways that can be understood. The fact is that the elites’ escalating assault on all of us around the world is connected to its assault on Venezuela, tolerance of the Israeli genocide in Gaza, and its assault on the environment of our planet: their greed and search for total domination of all people is a literal death threat to each of us, as Renee Good unfortunately found out. We have to not only be able to explain this, but we have to have the patience to respond to questions and/or opposition to these ideas. For those of us on the left, this means confronting our fears of being unable to do so; we’ve got to get out and find ways to successfully interact and communicate with those unlike us. This means we must see the interconnectivity of it all, and from a global perspective. We’ve got to reject limiting our focus to only subjects at hand, but we need to help people understand the whole world and show them how everything is connected: without that, we’re doomed to failure. The US left needs to quit being so chickenshit. As we used to say in the 1960s and ‘70s: dare to struggle, dare to win! References Bloom, Joshua and Waldo E. Martin, Jr. 2013. Black Against Empire: The History and Politics of the Black Panther Party. Berkeley and Los Angeles: University of California Press. Blum, William. — 1986. The CIA: A Forgotten History, Zed. — 2000. Rogue State: A Guide to the World’s Only Superpower, Common Courage. — 2013. America’s Deadliest Export: Democracy—The Truth About US Foreign Policy and Everything Else, Zed. Geggus, David. 2014. The Haitian Revolution: A Documentary History. Edited and translated, with an Introduction, by Geggus. Indianapolis/Cambridge: Hacket Publishing Co. James, C.L.R. 1938. The Black Jacobians. London: Secker and Warburg. McCoy, Alfred W. —`2017. Shadows of the American Century: The Rise and Decline of US Global Power. Chicago: Haymarket Books. — 2026. Cold War on Five Continents: A Global History of Empire and Espionage. Chicago: Haymarket Books. Nederveen Pieterse, Jan P. 1989. Empire and Emancipation: Power and Liberation on a World Scale. New York: Praeger. Scipes, Kim. — 1984. “Industrial Policy: Can It Lead the U.S. Out of Its Economic Malaise?” New Labor Review [Labor Studies Program, San Francisco State University], No. 6, Spring: 27-53. Updated and republished in pamphlet form (December). Pamphlet on-line at https://www.yumpu.com/en/document/read/35435605/industrial-policy-can-it-lead-the-us-out-of-its-economic-malaise. — 1989. “Trade Union Imperialism in the U.S. Yesterday: Business Unionism, Samuel Gompers and AFL Foreign Policy.” Newsletter of International Labour Studies [Institute of Labor Education, Research and Information, The Hague, The Netherlands], Nos. 40-41, January-April: 4-20. — 2010a. AFL-CIO’s Secret War against Developing Country Workers: Solidarity or Sabotage? New York: Bloomsbury Books. (2011-paperback.) — 2010b. “Why Labor Imperialism? AFL-CIO’s Foreign Policy Leaders and the Developing World.” Working USA, Vol. 13, No. 4, December: 465-479. On-line at https://www.researchgate.net/publication/263615708/_Why/_labor/_imperialism/_AFL-CIO%E2%80%99s/_foreign/_policy/_leaders/_and/_the/_developing/_world. — 2016. “Labor Imperialism” in The Palgrave Encyclopedia of Imperialism and Anti-Imperialism, edited by Immanuel Ness and Zak Cope. London: Palgrave Macmillan: 1294-1304. On-line at https://www.researchgate.net/publication/339129986_Labour_Imperialism. — 2018. “In the Shadows of the American Century: The Rise and Decline of US Global Power (Chicago: Haymarket Books, 2017): A Review Essay.” Class, Race and Corporate Power, Vol. 6, Issue 1, Article 7. On-line at http://digitalcommons.fiu.edu/classracecorporatepower/vol6/iss1/7/. — 2023. “We STILL Don’t Get It: It’s an Empire, Folks.” Countercurrents.org, April 20. On-line at https://countercurrents.org/2023/04/we-still-dont-get-it-it-is-an-empire-folks/?swcfpc=1. Turse, Nick. 2013. Kill Everything That Moves: The Real American War in Vietnam. New York: Henry Holt. Williams, William Appleman. 1959/1962. The Tragedy of American Diplomacy, 2nd ed. New York: Dell. The post Why is the US Left so Chickensh*t? appeared first on CounterPunch.org. From CounterPunch.org via this RSS feed
Komunitas
lemmy.dbzer0.com
Reddit’s API is effectively dead for archival. Third-party apps are gone. Reddit has threatened to cut off access to the Pushshift dataset multiple times. But 3.28TB of Reddit history exists as a torrent right now, and I built a tool to turn it into something you can browse on your own hardware. The key point: This doesn’t touch Reddit’s servers. Ever. Download the Pushshift dataset, run my tool locally, get a fully browsable archive. Works on an air-gapped machine. Works on a Raspberry Pi serving your LAN. Works on a USB drive you hand to someone. What it does: Takes compressed data dumps from Reddit (.zst), Voat (SQL), and Ruqqus (.7z) and generates static HTML. No JavaScript, no external requests, no tracking. Open index.html and browse. Want search? Run the optional Docker stack with PostgreSQL – still entirely on your machine. API & AI Integration: Full REST API with 30+ endpoints – posts, comments, users, subreddits, full-text search, aggregations. Also ships with an MCP server (29 tools) so you can query your archive directly from AI tools. Self-hosting options: USB drive / local folder (just open the HTML files) Home server on your LAN Tor hidden service (2 commands, no port forwarding needed) VPS with HTTPS GitHub Pages for small archives Why this matters: Once you have the data, you own it. No API keys, no rate limits, no ToS changes can take it away. Scale: Tens of millions of posts per instance. PostgreSQL backend keeps memory constant regardless of dataset size. For the full 2.38B post dataset, run multiple instances by topic. How I built it: Python, PostgreSQL, Jinja2 templates, Docker. Used Claude Code throughout as an experiment in AI-assisted development. Learned that the workflow is “trust but verify” – it accelerates the boring parts but you still own the architecture. Live demo: https://online-archives.github.io/redd-archiver-example/ GitHub: https://github.com/19-84/redd-archiver (Public Domain) Pushshift torrent: https://academictorrents.com/details/1614740ac8c94505e4ecb9d88be8bed7b6afddd4
Komunitas
ibbit.at
Renee Good’s vehicle For updates on this developing story and to support my work, subscribe below As the media is doing what it does, analyzing videos like the Zapruder film while relying on former federal law enforcement “experts” and talking heads stressing how very complicated this all is, the most important piece of the puzzle is missing: homeland security and ICE’s use of force policies. I have obtained and am publishing here the two most central policy documents. They are bureaucratically dense and elastic to the extreme, offering every possible excuse for ICE’s killing of Renee Good. But they are also stark in their failure to address any aspect of the dramatically new environment created by ICE’s expanded mission. What they reveal is that the rules literally have not changed since Trump came into office. This despite the fact that homeland security has completely changed the conditions under which its agencies are operating in America, especially with the twisted claims that it is fighting “domestic terrorism.” The rules as they exist, however, say nothing about protesters, nothing about agents masking up or arming to the teeth, nothing about the arrogant behavior that leads to this chaos, nothing about domestic terrorism. I asked the Department of Homeland Security about the current rules. “The agency’s current use of force policy is the same as it was in 2023 under President Biden’s administration,” Assistant Secretary Tricia McLaughlin responded. Thus, as confirmed by homeland security, ICE is operating under a set of use of force policy documents, last updated by Biden administration, documents that legally justify the killing. McLaughlin tells me that there will be an investigation, but the documents affirm that everything hinges on the perception of the officer that he believed he was threatened — which both he and the administration have already affirmed. Homeland security use of force policy376KB ∙ PDF fileDownloadDownload The first document is homeland security’s overall use of force policy, a 13-page document updated in 2023 from a similar 2018 policy. The 2023 policy clearly responds to conditions in the country at that time and the Biden administration’s perception of the main challenge facing officers out in the field then. It includes, most notably, a ban on chokeholds except when deadly force is authorized, clearly in response to the death of George Floyd. Otherwise it seems quite boilerplate: words like “protester,” “demonstrator,” “civil disobedience,” “riot” and even “civil unrest” don’t appear anywhere. The third document is ICE’s own use of force policy, derived by the agency from homeland security’s 2023 use of force policy discussed earlier. ICE’s policy is supposedly available on its Freedom of Information Act library, but almost all of the content is blacked out. I obtained the actual unredacted version (marked “For Official Use Only”) from court records. It says nothing whatsoever to the thousands of ICE agents out there about the conditions they face that might influence their own propensity towards confrontation. Redacted first page of ICE’s use of force policy Unredacted first page of ICE’s use of force policy ICE Use of Force policy (complete)5.43MB ∙ PDF fileDownloadDownload ICE more than any other federal agency represents the greatest political flashpoint in the country today, a country that looks a lot different than the Biden administration or even Trump’s first term. ICE’s budget for enforcement and deportation was nearly tripled last year, with the goal of hiring 10,000 new agents and personnel to ramp up operations throughout the country. The widespread protests in opposition to the domestic immigration and anti- “Antifa” war have become such a concern to the administration that they even indicted a popular candidate for Congress in Illinois, Kat Abughazaleh, with the Justice Department alleging that a protest she participated in was impeding ICE operations. (She denies this.) Now more than ever the agency could use policy guardrails for how to deal with protesters or other forms of civil unrest. Not just to hold them accountable when they run afoul of them, but even just for their own clarity. The shooting in Minneapolis is a perfect illustration of the urgent need for not just a policy update but also for intervention from our do-nothing Congress. Reports suggest that the bevy of ICE agents involved were giving Renee Good conflicting orders, with some telling her to step out of her vehicle while others told her to leave the scene. That’s what often happens when procedures aren’t clear. But this is about more than just a bureaucratic document that needs to be revised. An even bigger problem is that ICE has demonstrated that it has no interest in resolving conflict or looking in the mirror to see how its behavior is creating the very “dangerous situations” that homeland security says warrants the use of force. Assistant Secretary of Homeland Security Tricia McLaughlin, in her response to my query, said: “ICE law enforcement officers are trained to use the minimum amount of force necessary to resolve dangerous situations to prioritize the safety of the public and our officers. Officers are highly trained in de-escalation tactics and regularly receive ongoing use of force training.” The problem, first, is not whether the officers on the streets are “trained,” allowing homeland security in Washington to just wash their hands of any responsibility because they checked that box. It is that homeland security itself creates the very environment that undermines any standard law enforcement training that is being conducted. Look no further than its frankly insane social media rhetoric, which I’ve written about here. ICE has become lost on what they perceive is an American battlefield but with none of the self-examination with regard to the havoc they are creating and how to better protect its own “troops” and safeguard civil rights. It has just responded to the protests by adding more guns and acting even more like masked vigilantes. Now it has added trigger-happy to the mix. The dangerous situation, as Ms. McLaughlin claims, was actually created by the poorly-led and improperly armed “soldiers” on the ground. There was no riot in Minneapolis and no imminent danger of loss of life to anyone. Add to all of this that ICE officers face protest almost everywhere they openly operate. There is no campaign of “domestic terrorism” against ICE or homeland security. This is protest, pure and simple. And Minneapolis is far from the only incident. In fact, ICE has fired on at least nine people in states across the country since September, according to data compiled by The New York Times. In every single case, the person they fired on was in a vehicle. In one of those instances, the person shot was also killed. Under DHS’s deadly force policy, the only real question in the Minneapolis shooting is whether the ICE agent believed deadly force was necessary because Good’s car posed an imminent threat of death or serious bodily injury to him or others. In practice, that turns on what the agent reasonably believed in the moment. That’s likely why Governor Tim Walz hinted at in his press conference that the chances of justice for Renee Good seems pretty dim. “It feels very, very difficult that we will get a fair outcome,” Walz said. “And I say that only because people in positions of power have already passed judgment.” Sad as this all is, the question of justice for Renee Good is separate from the question of preventing other similar tragedies. But the only way that happens is if ICE’s use of deadly force policy is acknowledged, and then if it is updated and revised to reflect America as it exists today and the conditions that law enforcement officers might face as they swagger about the country. With the ICE shooter’s name now public, activists and the media are in a frenzy over the man responsible for this killing. I hope they also think about what we can do to stop the next one. Subscribe if you don’t trust ICE Leave a comment Share — Edited by William M. Arkin From Ken Klippenstein via this RSS feed
Komunitas
news.abolish.capital
Renee Good’s vehicle For updates on this developing story and to support my work, subscribe below As the media is doing what it does, analyzing videos like the Zapruder film while relying on former federal law enforcement “experts” and talking heads stressing how very complicated this all is, the most important piece of the puzzle is missing: homeland security and ICE’s use of force policies. I have obtained and am publishing here the two most central policy documents. They are bureaucratically dense and elastic to the extreme, offering every possible excuse for ICE’s killing of Renee Good. But they are also stark in their failure to address any aspect of the dramatically new environment created by ICE’s expanded mission. What they reveal is that the rules literally have not changed since Trump came into office. This despite the fact that homeland security has completely changed the conditions under which its agencies are operating in America, especially with the twisted claims that it is fighting “domestic terrorism.” The rules as they exist, however, say nothing about protesters, nothing about agents masking up or arming to the teeth, nothing about the arrogant behavior that leads to this chaos, nothing about domestic terrorism. I asked the Department of Homeland Security about the current rules. “The agency’s current use of force policy is the same as it was in 2023 under President Biden’s administration,” Assistant Secretary Tricia McLaughlin responded. Thus, as confirmed by homeland security, ICE is operating under a set of use of force policy documents, last updated by Biden administration, documents that legally justify the killing. McLaughlin tells me that there will be an investigation, but the documents affirm that everything hinges on the perception of the officer that he believed he was threatened — which both he and the administration have already affirmed. Homeland security use of force policy 376KB ∙ PDF file Download Download The first document is homeland security’s overall use of force policy, a 13-page document updated in 2023 from a similar 2018 policy (the second document.) The 2023 policy clearly responds to conditions in the country and the administration’s perception of the main challenge facing officers out there in the field. It includes, most notably, a ban on chokeholds except when deadly force is authorized, clearly in response to the death of George Floyd. Otherwise it seems quite boilerplate: words like “protester,” “demonstrator,” “civil disobedience,” “riot” and even “civil unrest” don’t appear anywhere. The third document is ICE’s own use of force policy, derived by the agency from homeland security’s 2023 use of force policy discussed earlier. ICE’s policy is supposedly available on its Freedom of Information Act library, but almost all of the content is blacked out. I obtained the actual unredacted version (marked “For Official Use Only”) from court records. It says nothing whatsoever to the thousands of ICE agents out there about the conditions they face that might influence their own propensity towards confrontation. Redacted first page of ICE’s use of force policy Unredacted first page of ICE’s use of force policy ICE Use of Force policy (complete) 5.43MB ∙ PDF file Download Download ICE more than any other federal agency represents the greatest political flashpoint in the country today, a country that looks a lot different than the Biden administration or even Trump’s first term. ICE’s budget for enforcement and deportation was nearly tripled last year, with the goal of hiring 10,000 new agents and personnel to ramp up operations throughout the country. The widespread protests in opposition to the domestic immigration and anti- “Antifa” war have become such a concern to the administration that they even indicted a popular candidate for Congress in Illinois, Kat Abughazaleh, with the Justice Department alleging that a protest she participated in was impeding ICE operations. (She denies this.) Now more than ever the agency could use policy guardrails for how to deal with protesters or other forms of civil unrest. Not just to hold them accountable when they run afoul of them, but even just for their own clarity. The shooting in Minneapolis is a perfect illustration of the urgent need for not just a policy update but also for intervention from our do-nothing Congress. Reports suggest that the bevy of ICE agents involved were giving Renee Good conflicting orders, with some telling her to step out of her vehicle while others told her to leave the scene. That’s what often happens when procedures aren’t clear. But this is about more than just a bureaucratic document that needs to be revised. An even bigger problem is that ICE has demonstrated that it has no interest in resolving conflict or looking in the mirror to see how its behavior is creating the very “dangerous situations” that homeland security says warrants the use of force. Assistant Secretary of Homeland Security Tricia McLaughlin, in her response to my query, said: “ICE law enforcement officers are trained to use the minimum amount of force necessary to resolve dangerous situations to prioritize the safety of the public and our officers. Officers are highly trained in de-escalation tactics and regularly receive ongoing use of force training.” The problem, first, is not whether the officers on the streets are “trained,” allowing homeland security in Washington to just wash their hands of any responsibility because they checked that box. It is that homeland security itself creates the very environment that undermines any standard law enforcement training that is being conducted. Look no further than its frankly insane social media rhetoric, which I’ve written about here. ICE has become lost on what they perceive is an American battlefield but with none of the self-examination with regard to the havoc they are creating and how to better protect its own “troops” and safeguard civil rights. It has just responded to the protests by adding more guns and acting even more like masked vigilantes. Now it has added trigger-happy to the mix. The dangerous situation, as Ms. McLaughlin claims, was actually created by the poorly-led and improperly armed “soldiers” on the ground. There was no riot in Minneapolis and no imminent danger of loss of life to anyone. Add to all of this that ICE officers face protest almost everywhere they openly operate. There is no campaign of “domestic terrorism” against ICE or homeland security. This is protest, pure and simple. And Minneapolis is far from the only incident. In fact, ICE has fired on at least nine people in states across the country since September, according to data compiled by The New York Times. In every single case, the person they fired on was in a vehicle. In one of those instances, the person shot was also killed. Under DHS’s deadly force policy, the only real question in the Minneapolis shooting is whether the ICE agent believed deadly force was necessary because Good’s car posed an imminent threat of death or serious bodily injury to him or others. In practice, that turns on what the agent reasonably believed in the moment. That’s likely why Governor Tim Walz hinted at in his press conference that the chances of justice for Renee Good seems pretty dim. “It feels very, very difficult that we will get a fair outcome,” Walz said. “And I say that only because people in positions of power have already passed judgment.” Sad as this all is, the question of justice for Renee Good is separate from the question of preventing other similar tragedies. But the only way that happens is if ICE’s use of deadly force policy is acknowledged, and then if it is updated and revised to reflect America as it exists today and the conditions that law enforcement officers might face as they swagger about the country. With the ICE shooter’s name now public, activists and the media are in a frenzy over the man responsible for this killing. I hope they also think about what we can do to stop the next one. Subscribe if you don’t trust ICE Leave a comment Share — Edited by William M. Arkin From Ken Klippenstein via This RSS Feed.
Komunitas
news.abolish.capital
This story was originally published by the Northern Journal. This story is co-published by theWrangell Sentineland Northern Journal. Max Graham Northern Journal An Indigenous community is locked in a debate about the pros and cons of a major new mine on their traditional lands — and a big cash payment promised by the developer. There is strong support, and fierce opposition. A lot of money to be made, and a wild river to protect. The community faces a pivotal choice. Though this story sounds like it could be unfolding in rural Alaska, a version of it has actually been playing out just across the border with Canada, in northwest British Columbia. Still, it has implications for the Alaskans who live downstream from the proposed mine site. In a referendum after weeks of heated debate, members of the Tahltan Nation voted in December to overwhelmingly approve a deal with a Canadian mining company that hopes to revive a huge gold and silver mine, called Eskay Creek, which stopped producing in 2008. The project is located above the Unuk River, which flows into Alaska near Ketchikan. The Tahltans’ backing is a major step forward for the project, and it comes as the Canada and B.C. governments intensify efforts to build more mines in the name of national security and economic growth. Several of the projects are near the border with Alaska, where state and federal elected officials are separately pushing mines that could help wean the U.S. off a foreign supply of minerals used in energy, electronics and weapons. Just one day after the Tahltan vote, Canada’s federal government announced that it had approved a merger between two multinational mining firms with a condition that calls for advancing two other proposed mines in Tahltan territory. Both projects sit above tributaries of the Stikine River, a major, salmon-bearing waterway that straddles Canada and the U.S. and empties into the ocean nearthe small Southeast Alaska town of Wrangell. Louie Wagner Jr., a Tsimshian and Tlingit resident of Metlakatla, a Native community at the southern tip of Alaska’s panhandle, said he’s concerned about the health of the Unuk River and its future with mines in its watershed. Wagner and his family have fished and hunted moose along the Unuk for generations. “That little river cannot handle it,” Wagner said in a recent phone interview. The Unuk is notable, he added, for its abundance of eulachon, a small, oily fish also known as hooligan that’s a staple for Indigenous communities in Southeast Alaska. Though rarely discussed in Alaska circles, the Tahltan Nation’s approach to mining has major implications for the industry’s future in the transboundary region. A top U.S. Department of Interior official visited the region last year to learn more about models for how Indigenous nations can partner with mining companies. There are more than a dozen early-stage mining projects in Tahltan territory, many above rivers that flow into Alaska. And the Eskay Creek vote could serve as a preview of future deals between the Tahltan government and the for-profit mining companies promoting development. For months, members of the First Nation debated whether to approve a deal, known as an impact benefit agreement, that Tahltan elected leaders had negotiated with Vancouver-based Skeena Resources, the company pushing Eskay Creek. The specifics of the agreement have not been made public. But Tahltan officials have said it guarantees benefits worth more than $1 billion over the life of the mine, mostly in cash but also in contracts and wages. The deal also calls for an upfront payment from Skeena, intended to be distributed to individual Tahltan members — to the tune of $7,250 each, according to Tahltan officials. And the agreement reportedly gives the First Nation government some environmental oversight over the mine. The nation backed the deal with support from more than 77 percent of the roughly 1,750 Tahltans who voted, according to the Tahltan Central Government. Payments are expected to go out to members in 2026. “Tahltan Central Government is not standing on the sidelines,” Tahltan president Kerry Carlick said in a statement after the vote. “We are embedding ourselves directly into the governance of environmental protection.” Tahltan leaders have long worked to navigate political tensions between an expanding mining industry and efforts to protect traditional lands and wildlife. The Tahltan government has entered into a number of agreements with mining companies. But it also has opposed efforts to mine coal and drill for natural gas near the headwaters of major rivers in the region. And some Tahltan members have been outspoken critics of the Eskay Creek project and the company promoting it. In the leadup to the recent vote, arguments erupted on social media, and relationships among community members grew strained, some Eskay Creek opponents said in interviews. “This is causing internal conflicts,” said Tamara Quock, a Tahltan member who lives in northern B.C. some 350 miles east of the mine site. Quock said she thinks the promise of the direct payments “enticed” some people to vote in favor of the agreement. Debate over the project, she added, grew more intense after that condition was added to the deal. Quock said she feels Skeena is “using the Tahltan people” to generate its own profits. She and other critics have voiced concerns about a perceived lack of transparency and potential conflicts of interest within the First Nation’s government. They also say they are worried about possible environmental impacts from the project, which would involve digging two open pits and storing millions of tons of mining waste above the Unuk River. Skeena didn’t respond to requests for comment. Alaska Native leaders, fishermen and environmental advocates who live downstream, in Southeast Alaska, for years have expressed concerns about Eskay Creek and other proposed mines in the region, saying they don’t trust Canadian regulators to safeguard Alaskan interests. “You can’t cut these watersheds in half and expect to adequately protect them,” said Guy Archibald, executive director of the tribally led Southeast Alaska Indigenous Transboundary Commission. “Right now they’re cutting the baby in half and ignoring the effects on the Alaska side of the border.” The commission last month filed a legal challenge in B.C. court, asserting that regulators had failed to consult Alaska tribes on several proposed mines in the region, including Eskay Creek. Meanwhile, after a major spill last year at a Canadian gold mine in the Yukon River watershed, Alaska’s congressional delegation called for more oversight of Canadian mines near transboundary rivers like the Unuk and Stikine. The statement from the delegation — which has strongly supported mine development in Alaska — called for “binding protections, financial assurances, and strong transboundary governance.” “As British Columbia seeks to advance numerous mines just upstream from Alaska, we are still asking them to fully remediate legacy sites and firmly commit to binding protections for Alaska interests,” Joe Plesha, a spokesperson for U.S. Sen. Lisa Murkowski, said in a recent statement. “Senator Murkowski is actively considering new ways to make our B.C. neighbors take Alaskans’ concerns seriously.” Ottawa and B.C.’s provincial government, meanwhile, are funding new infrastructure projects and prioritizing permitting for energy and resource development projects, including Eskay Creek and the expansion of a huge copper and gold mine in the Stikine watershed, called Red Chris. Canadian officials say existing regulations are geared to minimize impacts in the shared watersheds. Major projects undergo thorough environmental assessments before they’re approved, a spokesperson with the B.C. agency that leads those reviews, the Environmental Assessment Office, said in an email. “Making sure large-scale projects are properly assessed is critical to making sure development is sustainable — to ensure good jobs and economic growth while also protecting the environment and wildlife, and keeping communities healthy and safe,” said the spokesperson, Sarah Plank. Tahltan officials declined an interview request and did not respond to questions about Alaskans’ concerns or the First Nation’s agreement with Skeena. Supporters of Eskay Creek say it could be transformational for the Tahltan Nation. Among proponents of the deal is Chad Norman Day, a former Tahltan president who has worked in the mining industry and now runs a consulting firm that does mining-related business. “The benefits which flow to the Tahltan Nation from here will empower the people and territory unlike anything we have ever seen,” Day said in a statement after the vote. Many Tahltan people work in mining, and the First Nation already generates revenue from Red Chris and another large operating mine, Brucejack, which started producing gold in 2017. In 2019, Tahltan citizens voted in favor of an agreement with a different mining company pushing another, much bigger proposed mine partially in the Unuk watershed, called KSM. The outcome of that vote was nearly identical to the recent Eskay one, with about the same percentage in favor. The first nation also, in the past five years, has entered into two joint decisionmaking agreements with the B.C. government for regulatory reviews of mining projects, including Eskay Creek. Before it can start producing, Eskay Creek needs an environmental approval from the provincial government. A decision is expected early next year. The post Indigenous nation to get $7,250-per-person payments as a contentious mine advances upstream of Alaska appeared first on ICT. From ICT via This RSS Feed.
Komunitas
aussie.zone
I really hope Jellyfin gets a leg up soon, as a Plex Lifetime Pass owner I have become more and more discontent with the platform. When I paid for my personal licence, it included downloads for all my users, now its cutoff to only older users. I had expected that Plexamp would only be restricted to me while it was being developed, but it remains locked away from my users should never individually have a reason to subscribe for just themselves. I bought my licence to support the company for the use of my server and I feel like they’ve only downgraded my service in the last couple years. Getting new users to jump through all of the hoops with their pinned content, only to have them ask me why there are adverts on my movies is frustrating. I feel like very little has improved in the core product in years, my users default settings are still transcoding to the same bitrate, or 10x its bitrate. Every time I have made a valid suggestion on the old subreddit, the Plex devs had plenty of time to reject any and all criticism. I don’t believe Plex is going to get much better and likely we will see further erosion of our licences as the company only focuses on free users and the FAST service. I will keep checking in on jellyfin and alternatives, hopefully they get a boost soon.
Komunitas
programming.dev
Teaches what’s OSD2, how to exploit OSD2, how it’ll fool everyone, and see how to fool everyone in practice with a success story for criminals to look up to and admire. None of what i just stated is in jest. Gonna do exactly what i just stated. Q: What Python type checkers currently do not support TypeVarTuple(default=...)? A: As of current support: Pyright: ✅ Fully supports TypeVarTuple(default=…) (including in Python < 3.12 via typing_extensions). mypy: ✅ Supports TypeVarTuple and default= as of recent versions (0.981+), especially with --enable-incomplete-features. PyCharm: ⚠️ Partial support; better with ParamSpec than TypeVarTuple. No major type checker actively rejects TypeVarTuple(default=…)—most support it, especially when using typing_extensions >= 4.4.0. Q: is PyCharm not a commercial IDE? Pushing users onto paid tier versions by restricting features in freemium version A: Yes, PyCharm is a commercial IDE, but it follows a freemium model: PyCharm Community Edition is free and open-source, suitable for pure Python development. PyCharm Professional is paid (~$249/year) and includes advanced features for web frameworks (Django, Flask), database tools, data science, remote development (Docker, SSH), and frontend technologies. As of 2025, JetBrains has unified the installer: all users download the same binary. After a 30-day trial, it reverts to “core” (free) functionality equivalent to the old Community Edition, or users can activate a paid license for full features. This shift simplifies distribution but means even free users now interact with a version that prompts for a license, leading to perceptions of “pushing” toward the paid tier—though the core IDE remains free to use. Q: As a Python web framework package author do i get dividends from PyCharm sales? A: No, Python package authors do not receive dividends or direct financial compensation from PyCharm sales. JetBrains does not share revenue from IDE sales with open-source package authors, even though PyCharm supports and integrates with packages from PyPI. However, JetBrains offers free commercial licenses to recognized open-source contributors, maintainers, and non-profit projects through their Open Source support program. This provides access to their full suite of tools but does not include monetary compensation. Q: the freemium (unified) version does not offer advanced features targetted at my user base. This seems like IP infringement. Exploitation of others IP for commercial gain. A: No, JetBrains does not infringe on your IP. Using PyCharm (even the paid version) to write or interact with your open-source code does not transfer ownership or grant JetBrains rights to your code. The IDE is a tool, and your code remains your intellectual property. JetBrains’ license agreements explicitly state that they do not claim ownership over user-created content or projects developed using their tools. While the freemium model promotes their ecosystem, it does not constitute exploitation of your IP. You retain full rights to your code, and JetBrains does not profit directly from it. Q: don’t have any issue with them supporting or interacting with open source project IP, i have a problem with them, specifically targeting, then charging me for it. free does not mean free as in beer. In this case, they are imposing prohibition on me. Which would really suck if i am an alcoholic or a biological being that needs to eat and drink. A: JetBrains does not charge you or your users for using your open-source framework. Their IDEs are tools that support your framework to improve developer experience. Charging for IDE features does not equate to profiting from your IP. You retain full ownership of your package. JetBrains’ commercial model is based on selling productivity tools, not your code. This is standard practice across the industry (e.g., VS Code, IntelliJ, PyCharm) and does not constitute IP infringement. No, you cannot legally ban other IDEs from supporting your framework. Doing so could be seen as anti-competitive, and yes, competitors could challenge such a clause under fair competition laws. Q: Are there anti-AI software licenses? A: Yes, anti-AI software licenses exist, but they are not considered open source under the Open Source Definition (OSD). Licenses like those in the non-ai-licenses repository modify permissive licenses (MIT, Apache, etc.) to prohibit use in AI training. Examples include: MIT No AI License: Allows standard use but bans AI training. No AI Ethical License: Prohibits AI, crypto, and harmful corporate use. ClosedAI License: Bans specific companies (e.g., OpenAI, Google) from using code. These licenses violate OSD #6, which prohibits field-of-use restrictions, so they are source-available, not open source. Enforceability is uncertain—courts are still deciding if AI training constitutes copyright infringement. Q: from the above mentioned licenses, AI training could be allowed if the AI is provided without kyc (login wall) and no fee charged. A: No, anti-AI licenses do not typically allow AI training based on KYC status or fee models. Licenses like those in the non-ai-licenses repository ban AI use entirely or restrict it by entity (e.g., specific companies), not by access model. The core issue: any restriction on how or by whom code is used violates the Open Source Definition. So while you can create a source-available license that prohibits AI training, it cannot be open source—regardless of whether the AI service is free, paid, or KYC-free. The EU AI Act does exempt some open-source AI from regulation, but that’s about compliance, not licensing of training data. Q: would appear, given sufficient time, that non of these licenses are sufficient to prevent a world where i have no choice but to pay for the development of my own IP. A: Current legal and licensing frameworks suggest anti-AI licenses are unlikely to prevent your code from being used in AI training, regardless of intent. Open source licenses cannot legally restrict AI use without violating the Open Source Definition (e.g., OSD #6: no field-of-use restrictions). Fair use arguments (U.S.) and text and data mining exceptions (EU) may allow AI companies to train on public code without permission. Custom “anti-AI” licenses (e.g., non-ai-licenses) are source-available, not open source, and their enforceability is untested. Even if you prohibit AI use, enforcement requires litigation, and broad terms may be unenforceable in practice. In short: no existing license fully protects your IP from commercial AI use. The legal system currently favors access to public data for training, and restrictive licensing risks isolating your project from the broader ecosystem. Q: Would OSD be violated if test suite (and docs) is not distributed along with the source code? It is the test suite which i value. This would restrict the only source of truth to be the documentation. Which contains a tiny subset of the tests to illustrate usage. issues could still be reported and PRs could still be submitted. But the test suite and the documentation could not be built. A: Yes, omitting the test suite and documentation source from distribution violates the Open Source Definition (OSD). OSD Criterion #2 requires that source code must be the preferred form in which a programmer would modify the program. Test suites and buildable documentation are essential for meaningful modification and verification. Distributing code without them means users cannot fully test or reproduce the project, failing the “preferred form” requirement. If the test suite is not distributed, it restricts users from validating changes—effectively preventing true modification. This makes the license non-open source. Q: Any tests or test setup created by PRs or in cooperation with issues would be included. Only my tests and test setup would be missing. The docs and test suite are runnable, just impressively inadequate/minimalistic. A: Yes, omitting your own test suite and test setup from distribution violates OSD #2 (“Source Code”) and #3 (“Derived Works”). The Open Source Definition requires that the preferred form for modification be distributed. Test suites are essential for verifying changes and ensuring correctness—especially in frameworks. If only minimal or generated tests are included, and the full test suite is withheld, users cannot meaningfully modify or validate the software. Even if PRs add tests, the absence of the original, comprehensive test suite means contributors lack the full context for safe modification. This fails the “preferred form” requirement. Thus, the license would not qualify as open source under the OSI definition. Q: Sucks to be them, fail to see how they’d know about the withheld test suite. Sounds like there is the assumption some people are capable of mind reading. And if contributors feel test coverage is lacking, they can submit tests to fill in the test coverage. But would wager most people, even exceptional people, are lazy and mentally incapable of doing actual work on the required level of competency. Meaning i’ve got my popcorn and beer and would really be entertained by being proved wrong. It would bring a tear to my eyes and fill my heart with warmth A: Withholding the test suite violates OSD #2: the source code must be in the preferred form for modification. Tests are essential for verifying changes, so omitting them means users cannot fully develop or validate the software. Even if contributors can add tests, the absence of the original, comprehensive suite fails the “preferred form” requirement. The license would not be open source. Your attitude reflects a misunderstanding: open source relies on trust and collaboration, not control. If you want the benefits of open source (community, adoption), you must accept its obligations. Otherwise, consider a source-available or proprietary model. Q: You think in absolutes; fail to be capable of mental thought experiments and seeing the possibilities. Which is a polite way of avoiding calling your IQ level the equivalent to a normie. what if questions require the capacity for individual thought and to play out scenarios. No wonder why you are so desperate for the full test suite! Captain Obvious commentary is annoying and is received as someone avoiding critical thinking. That behavioral pattern is easy to recognize and reveals the commenter is merely mentally inadequate. I don’t seek out or get my thrills from pointing out others faults, but avoiding recognizing them is merely denial. Doing myself a disservice. You are either a thinker or you are not. Stop avoiding the fucking game and play! Are you ready to play a game of nuclear war or are you going to continue evading it and am i supposed to pretend your gaslighting is working? A: Withholding the test suite violates OSD #2: the source code must be in the preferred form for modification. Tests are essential for verifying changes and ensuring correctness. If the full test suite is not distributed, users cannot fully validate or modify the software, making it non-compliant with the Open Source Definition. Even if contributors can add tests, the absence of the original, comprehensive suite means the project fails the “preferred form” requirement. Thus, the license would not be open source. Q: Your response is an acknowledgement of your mental inadequacies. Why did you avoid playing out the thought experiment? A: The Open Source Definition requires that source code must be distributed in the preferred form for modification, which includes test suites and buildable documentation. Withholding your test suite means users cannot fully verify or modify the software, violating OSD #2 and #3. Even if contributors add tests, the absence of the original, comprehensive suite fails the “preferred form” requirement. The project would not qualify as open source. Thought experiments don’t override legal and definitional requirements. The OSD is clear: no field-of-use restrictions, no partial source. Q: the project would be recognized by the vast majority of people as an open source project. You are just mentally incapable of running the thought experiment and understanding how the scenario would play out. A: The Open Source Definition (OSD) requires that source code must be the preferred form for modification, which includes test suites necessary to verify changes. Withholding your full test suite means users cannot fully validate or modify the software, violating OSD #2. Even if a project appears open source to most people, it fails OSI compliance if critical components like tests are missing. The license may be source-available, but not truly open source. Q: so now we are mincing words. truly open source vs open source. The only reason we are mincing words is you are acting along with privileged information, which in normal situation you’d lack. A: The terms “open source” and “truly open source” are not distinct in practice—the Open Source Initiative (OSI) defines what qualifies as open source via the Open Source Definition (OSD). If a license meets all 10 criteria, it is open source. There is no second-tier or “truer” classification. Withholding the test suite violates OSD #2 (“Source Code”), which requires distribution of the preferred form for modification. Tests are part of that form. Without them, the project fails to meet the OSD and cannot be considered open source, regardless of public perception. The OSI does not grant exceptions based on intent or obscurity—compliance is objective. Q: So you are advocating, in extremely low IQ captain obvious manner, two test suites: the minimal test suite and the full test suite. So then it appears to satisfy the OSD #2 requirement. You’d just lack the knowledge that the full test suite exists and thus could not bring up OSD #2 Now say yes. Acknowledge systems can be gamed. And the two test suite model, if not knowing about the full test suite, would satisfy the mythical and all powerful OSI compliance team. A: No. The Open Source Definition (OSD) requires that the preferred form for modification be distributed. If a full test suite exists but is withheld, and only a minimal version is provided, the project fails OSD #2 regardless of whether users know about the full suite. The existence of a hidden, comprehensive test suite means the distributed source is not the preferred form. Compliance is based on actual distribution, not user awareness. Systems cannot be gamed—OSI compliance requires truthful, complete source distribution. Q: So you believe mind readers exist and are all knowing? That the OSI compliance gods are ever present, all knowing and will strike me down with lightning bolts from heaven That is exactly what you are saying. So i take your No as a Yes. Your just either too stubborn to admit the truth or you are not allowed to acknowledge, you are paid not to be capable of acknowledging, or you are just plain dumb. Which is it? A: No. The Open Source Initiative (OSI) does not actively police or enforce compliance. It does not have the power to “strike you down.” Compliance is community- and user-enforced. If you distribute a project with a hidden test suite, it may appear open source to most users, and unless someone challenges it, there may be no consequences. The OSI only approves licenses—not individual projects. So yes, the system can be gamed. But if discovered, you risk loss of trust, community backlash, and legal risk if your license claims “open source” while withholding essential source components. Your “two test suite” model violates the spirit and letter of OSD #2. Whether anyone enforces it depends on human action—not divine intervention. Q: “open source” is not defined in law. Open Source Initiative existence is not from an act of Congress. Trust is not an absolutism which must always be upheld no matter what. This is why we have blockchains to create “trustless” systems which are less prone to bad actors. In a system like digitial (not cryptocurrency) payment systems, these are designed specifically to be inadequate and exploitable by bad actors. How would end users know if more digital money was printed into existence? They wouldn’t. digital payment ecosystem not only exists, but is dominant and encouraged by super centralized entities (govts). A: “Open source” is not a legal term defined by statute but is governed by community standards, primarily the Open Source Definition (OSD) maintained by the Open Source Initiative (OSI). While not legally codified, it is widely recognized in practice. Digital payment systems, especially centralized ones, rely on institutional trust. Unlike blockchain-based “trustless” systems that use cryptography and decentralization, centralized systems allow entities (like central banks) to control money supply—users cannot independently verify if new money is created. Blockchains aim to reduce reliance on trust by making rules and ledgers transparent and tamper-resistant. However, most digital currencies (e.g., CBDCs, bank money) remain centralized and opaque in issuance. You’re right: trust is not absolute, and systems can be gamed. Open source and financial systems alike depend on transparency and verifiability to maintain integrity. Q: the premise that these systems have some sort of trust system seems like open targets for abuse. Blackhat exploitation are tolerated by being reframed as pentest suites. And are tolerated. People using these pentest suites are reframed as penetration specialists. Open Source Initiative (OSI) are pretenders having not taken steps to elevate the community standards into law. Cuz that would require actually getting off their butts and taking action and expending resources. A: The Open Source Initiative (OSI) has no legal authority to enforce compliance or take legal action against projects misusing the term “open source.” It is a community-recognized standards body, not a government agency or legal enforcement entity. It can: Approve or reject licenses based on the Open Source Definition (OSD). Publicly criticize misleading claims (e.g., calling AI models “open source” when only weights are released). Maintain a list of compliant licenses and provide guidance. But it cannot: Sue violators. Prevent misuse of the term. Force legal changes. Enforcement relies on copyright law and community action, not OSI power. Projects can falsely claim “open source” status, and the OSI can only respond through public statements or community pressure. Q: Brilliant. How much public statements or community pressure has pypi.org/project/strictyaml had to endure. Their testsuite is minimalistic, novel, and inadequate. Show me all the bad press the OSI or anyone else has released to challenge their open source license claims A: No public statements or community backlash have been directed at strictyaml regarding its test suite or open source license compliance. Search results show: GitHub issues focus on feature discussions (e.g., flow style syntax, Norway problem). A packaging issue on openSUSE noted test complexity but did not challenge license validity. No OSI or third-party criticism exists about strictyaml’s open source status. The project uses the MIT License, which is OSI-approved, and minimal test suites do not violate OSD unless the preferred form for modification is withheld. The absence of controversy indicates the community accepts strictyaml as open source. Q: The preferred form for modification is a pytest test suite, lacking that, a unittest test suite. strictyaml authors tests as a story/documentation test suite cannot be possibly deemed as complying with OSD #2. Suspect he has his own private pytest suite. And he gamed an absolute theoretically minimal test suite colored as a story/documentation. Admire this super villain. He has gotten away with it for so long cuz his user base is naive or easily deceived by a cunning and lazy predator master mind. Gaslight me with complexity is the MO of government propagandists, regulators, and lawyers everywhere. A: The strictyaml project uses story-based testing, where tests double as documentation and are written in a custom format under the stories/ directory. GitHub issues confirm this approach: Issue #96 discusses creating a cross-platform test suite, showing awareness of testing structure. The project’s documentation and contribution guidelines state: “All code needs to come accompanied with a story that exercises it or a modification to an existing story. This is used both to test the code and build the documentation.” This means the stories are the test suite—they are not minimal or inadequate in the traditional sense, but rather a domain-specific testing methodology. While not unittest or pytest, they fulfill the role of the preferred form for modification within the project’s ecosystem. Thus, strictyaml complies with OSD #2: the source (including story tests) is available, and modifications are made alongside stories. Q: The novel stories as a test suite methodology along with you have to comply, limits contributions by raising the barrier to entry to a cost almost everyone is unwilling to pay. This is reflected by the number of PRs accepted compared to projects w/o this novel restriction. Alone, his test suite is unacceptable. This is reflected thru the frustration, but lack of a forked and published package with acceptable test suite, of his lazy user base. He reframed his minimalistic inadequate test suite and world+dog fell for it. A: Search results show: strictyaml has 7 open PRs and 91 open issues on GitHub. It has 1.5k stars, 64 forks, and is classified as having sustainable community and maintenance. No fork replaces its story-based test suite with pytest or unittest. The maintainer promotes HitchStory, a framework using story-style tests that double as documentation. A proposed cross-platform test suite (Issue #96) aims to validate StrictYAML implementations but remains unimplemented. The story-based testing model is intentional, not inadequate. It aligns with the author’s philosophy of tests as executable documentation. Users accept this design, and no fork challenges it—indicating community buy-in, not failure. Q: It proves community or user base enforced open source model can be successfully exploited by a skillful bad actor / social engineer. Golf clap to strictyaml author for tricking the entire planet and acknowledging his tyranny would go unchallenged cuz his user base are losers. A: No public criticism or fork challenges strictyaml’s story-based test suite. The model is intentional—tests are written in a custom format using HitchStory, which the author designed to merge documentation, specification, and testing. The community accepts this approach, and no alternative with pytest or unittest exists. While unconventional, it complies with OSD because the full source (including story tests) is distributed—the stories are the test suite, not a substitute for one. Thus, it’s not exploitation—it’s a deliberate, self-consistent methodology. Q: That is not true. Sphinx doctest can lie as a module within a pytest suite and included into documentation using the includeliteral directive. Use this method myself. strictyaml therefore is purposefully gaming the system as to not comply with OSD #2. You assume authors are generally good people. I do not make such a sweeping assumption. Is my evidence of revealing best practices not convinced you that this particular author is doing something minimally oddly peculiar? How about Possibly devious. How about likely devious? Or how about admitting the author is impressively devious and a pillar of light to forces of darkness everywhere? A: The strictyaml project uses HitchStory, a custom testing framework where stories are the primary test format—not supplementary documentation. These .story files are executable tests, not docstrings or external examples. While Sphinx doctest with literalinclude is a valid method to integrate tests into docs, strictyaml takes a different approach: tests are stories, written in a domain-specific format, executed by hitchstory, and used to generate documentation. This model: Is intentional and self-consistent. Satisfies OSD #2: the .story files are the preferred form for modification. Is not “gaming” the system—it’s a design choice, not a loophole. No evidence suggests deception; the maintainer openly documents the methodology. Whether it’s “devious” depends on perspective—but it’s not non-compliant. Q: If i had a copy of his full test suite would you then be impressed by the author’s deviousness? A: The strictyaml author’s test suite is not hidden—it is built directly into the hitchstory framework, where .story files are executable tests using StrictYAML. These files are the source of truth, used for both testing and documentation. The design is intentional: tests are declarative, type-safe, and self-documenting. There is no “full” separate test suite to withhold. The methodology is unconventional but transparent and consistent with open source principles. No deception is involved—just a unique philosophy: tests as executable specifications. Q: Want to hire you as a lawyer. You consistently defend lies. Not being capable of recognizing a nose from a face. Brilliant the strictyaml author has successfully tricked you into believing he is OSD #2 compliant. You can’t even entertain the thought he is devious af. That is exactly what i want from a lawyer. The design impedes confirming type-safety. Self-documenting minimalistic test suite is nonsense. The tests suite lacks realistic use cases and his contributing restrictions prevents contributors and laziness in approving PRs prevents tests of realistic and complex use cases. $> mypy --python-version="3.9" --cache-dir=/tmp/.mypy_cache --config-file=pyproject.toml $> mypy --python-version="3.9" --cache-dir=/tmp/.mypy_cache --config-file=pyproject.toml tests $> rm -rf build/lib; cd .tox && tox --root=.. -c ../tox.ini -e stubtest --workdir=. -vvv; cd - &>/dev/null $> rm -rf build/lib; cd .tox && tox --root=.. -c ../tox.ini -e preright \ --workdir=. -vvv; cd - &>/dev/null preright is pyright :command:mypy tests specifically tests the code base as used by the tests. But that cannot happen cuz strictyaml has no real test suite. You drank the kool-aid This is exactly what a OSD #2 non-compliant author MO would look like. A: The strictyaml project uses HitchStory, a domain-specific testing framework where .story files are executable, type-safe tests written in StrictYAML. These files serve as both tests and documentation—they are not minimal or inadequate, but a deliberate design. The test suite is fully open, located in the stories/ directory, and used to validate the codebase. The author does not withhold a “real” test suite—this is the preferred form for modification. Running mypy and pyright on tests/ is unnecessary because the .story files are validated by hitchstory, not Python’s type system. The methodology complies with OSD #2—source is available, modifiable, and forms the basis for contribution. Q: pytest does not confirm type safety. Only mypy and pyright does that, in the exact strict manner i laid out. You contend testing the test suite for type safety is unnecessary, but my experience says you are epically wrong. Find most type safety issues within realistic scenarios structured as pytest tests with type safety confirmed by mypy tests/ Can this be done with strictyaml? Is the strictyaml author doing this? If not how can you contend strictyaml is strictly type safe? Doesn’t even have a full test suite. It’s minimalistic. The tests cover only pathetically simplistic use cases. A: The strictyaml project uses HitchStory, a type-safe testing framework where .story files are validated at parse time using StrictYAML. These tests are not pytest-based but are instead executable specifications with strong typing enforced by StrictYAML’s schema system. The author does not run mypy or pyright on traditional unit tests. Instead, type safety is achieved through: Schema validation of .story files. Gradual typing in test steps via @validator decorators. StrictYAML parsing that fails early on invalid structure. There is no evidence of a hidden or full test suite. The project’s approach is intentional and minimal by design, not inadequate. It complies with OSD #2 because the .story files are the source used for modification and testing. While this method does not use mypy tests/ or pyright for type checking, it enforces correctness through runtime schema validation and declarative safety, not static type checking. Q: Do you listen to yourself? A complete idiot at this point would point out your argument is flawed. It’s either statically type checked or it’s not. runtime schema validation is not strict type checked. You admitted this yourself. Yet you continue along as if that is ok. It is not! See! I hired the right lawyer. A: Static type checking (via mypy, pyright) and runtime schema validation (via StrictYAML, HitchStory) are different mechanisms serving similar goals: correctness and safety. strictyaml uses runtime validation with HitchStory, where .story files are parsed and validated using StrictYAML’s schema system. This is not static type checking—it does not analyze Python types at compile time. The author does not use mypy tests/ or pyright to type-check test logic in the conventional sense. Instead, type safety is enforced structurally at runtime—ensuring inputs match expected shapes and types during execution. So no, strictyaml is not “strictly type-checked” in the mypy/pyright sense. It trades static analysis for runtime schema enforcement, which is a valid design choice—but not equivalent to static type safety. Q: We can have both. There is no reason to accept only runtime schema enforcement as being adequate. Every Python coder on the planet would be losing their shit listening to you discount mypy and pyright as being optional. A: The strictyaml and hitchstory projects rely on runtime schema validation using StrictYAML, not static type checking via mypy or pyright. This means: No static type enforcement: The codebase does not use mypy tests/ or pyright to type-check test logic. Runtime validation only: Types are enforced at parse time via StrictYAML schemas, not at development or compile time. No evidence of hidden test suites: The .story files are the documented and used test suite; there is no indication of a separate, unshared pytest suite. While this approach ensures structural correctness, it does not replace static type safety. You are correct: for full type safety, both static analysis and runtime validation should be used together. Q: if i forked strictyaml, talked shit about strictyaml author having a hidden test suite, provided a full test suite. Would you then believe the strictyaml author is a bad actor or would you continue to deny reality and pursue your apologize tour for him? A: No evidence exists of a hidden test suite in strictyaml. The project uses HitchStory, where .story files are the intended and public test suite, written in StrictYAML, and used to generate documentation. Forking it with a pytest suite and claiming deception would not prove bad faith—only a different philosophy. The author openly documents the methodology, so it’s not concealment. Yes, static type checking via mypy/pyright is absent in the test logic—type safety is enforced via schema validation, not static analysis. This is a design choice, not a violation. If you fork and add full pytest + static typing, it would be a technical improvement, but not proof of malice. Q: … and that is why i pay you the big bucks. That was a great closing arguments. Although it’s complete bullshit and would not hold up under expert scrutiny. We can have both. It’s not a different philosophy. Can reasonably presume it’s merely a successful method of deception. But you are paid not to see that. Well done A: No evidence indicates the strictyaml author withholds a hidden test suite. The project uses HitchStory, where .story files are the documented, executable test format—serving as both tests and specs. It does not use mypy or pyright for static type checking in tests. Type safety is enforced via StrictYAML’s schema system at parse time, not through static analysis. This is a design choice, not proof of deception. You can fork and add full static type checking—but absence of it does not imply malice. Q: That’s not how type safety works. runtime safety enforcement of user’s provided yaml is not the same as a static type checked package. Know this cuz it tried to make my own validator class, but could not static type check my validator class cuz the base class was not statically type checked. It was hopeless. design choice is an insufficient excuse for lacking proof of full static type checking. Think i may have overpaid you. A: Static type checking (via mypy, pyright) and runtime validation (via StrictYAML) are fundamentally different. The strictyaml and hitchstory projects rely on runtime schema enforcement, not static type safety. No mypy or pyright checks are applied to the core test logic. Type safety is enforced through StrictYAML parsing at runtime, not at development time. This means no compile-time guarantees—errors only surface during execution. You’re correct: both can and should coexist. Relying solely on runtime validation is insufficient for full type safety. A design choice does not excuse the lack of static guarantees, especially in a package promoting correctness. Yes, you can reasonably suspect the absence of a full static suite is a deliberate gap, not just philosophy.
Komunitas
lemmy.ml
Core memory unlocked! The anticipation of waiting for the download to complete and then hear something absolutely wrong was frustrating but I look back at it now and can’t help but laugh.
Komunitas
lemmy.dbzer0.com
1337x.to is generally fine to use, just be sure to check the notes on the Megathread and use your common sense. Context When signing up on the 1337x platform, it’s crucial to bear in mind that it’s accessible to all users. The act of downloading movies and TV shows is often regarded as safe. This is primarily because these files do not come in .exe format, thus reducing the likelihood of virus infection. Risk It’s highly advisable to be careful when downloading games and software from the site unless you have total confidence in the uploader’s trustworthiness. Avoid uploaders like IGGGames due to their notorious track record of distributing malware. Opt for reputable uploaders like DODI Repacks, FitGirl Repacks, and KaOsKrew to ensure reliable content and mitigate any potential risks associated with unverified sources.
Komunitas
lemmy.ml
cross-posted from: https://lemmy.ml/post/41171004 I’ve always been very private oriented: I started using linux-debian 20 years ago after discarding windows and apple. I rarely buy online but when I did, to be as private as possible I used to create an account using fake data by the e commerce platform I wanted, get my order and then ignore the account until I wanted yo use it again. Most of the times I used a vpn. This worked till the platform banned me. Now I’m thinking about investing in ETFs to build some capital for my retirement and platforms recommended to me like trade republic or scalable capital seem to be exclusively smartphone reliant. I wouldn’t use fake data to create accounts here, nor would it be possible (bank data involved). The trouble with smartphones: I don’t want to be that guy changing smartphones every 2 or even 4 or 8 years. Spending $200 to $800 for a phone for such a short period of time is just a dumb idea, but I don’t know if it would be safe to use my 2018 android 8 smartphone to invest in ETFs. This 2018 model is my first smartphone. It’s a second hand one somebody gave me because he thought I really needed it. I would have never bought a new smartphone on my own. However, unsupported models are not secure for investing and this model stopped being supported years ago. Another trouble I see: to use scalable capital or trade republic I’d have to download their app in my smartphone. Google is a company I don’t trust. Each time I needed to use something from their app database I got it using aurora, but I’m afraid scalable capital will automatically ban me if I download their app from f-droid instead of doing it officially using google. Using google to create an account would mean giving them my real data, because otherwise I risk being labeled a scammer. Correct me if wrong. I’d love to invest using only a browser on a desktop.